© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 13677
    Prev
    Next
    INDEX
    Explanations

    numbers representing the amount of casualties in violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to casualty figures from violent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disclaimer
    -0.83
    flush
    -0.75
    inventoryQuantity
    -0.75
    produced
    -0.71
     evolves
    -0.70
    soType
    -0.68
    soDeliveryDate
    -0.68
     Transactions
    -0.66
    CHO
    -0.65
    given
    -0.65
    POSITIVE LOGITS
     innocent
    0.97
     bystanders
    0.93
     civilians
    0.91
     unarmed
    0.87
     pedestrians
    0.82
     occupants
    0.78
     victims
    0.78
     fleeing
    0.78
     protestors
    0.75
     innoc
    0.73
    Activations Density 0.178%

    No Known Activations